public class ArabicTreebankParserParams extends AbstractTreebankParserParams
TreebankLangParserParams
implementing class for
the Penn Arabic Treebank. The baseline feature set works with either
UTF-8 or Buckwalter input, although the behavior of some unused features depends
on the input encoding.Modifier and Type | Class and Description |
---|---|
protected class |
ArabicTreebankParserParams.ArabicSubcategoryStripper |
AbstractTreebankParserParams.AnnotatePunctuationFunction, AbstractTreebankParserParams.RemoveGFSubcategoryStripper, AbstractTreebankParserParams.SubcategoryStripper
evalGF, generateOriginalDependencies, inputEncoding, outputEncoding, tlp
Constructor and Description |
---|
ArabicTreebankParserParams() |
Modifier and Type | Method and Description |
---|---|
AbstractCollinizer |
collinizer()
The collinizer eliminates punctuation
|
AbstractCollinizer |
collinizerEvalb()
Stand-in collinizer does nothing to the tree.
|
java.util.List<? extends HasWord> |
defaultTestSentence()
Return a default sentence for the language (for testing).
|
DiskTreebank |
diskTreebank()
Allows you to read in trees from the source you want.
|
void |
display()
Display (write to stderr) language-specific settings.
|
HeadFinder |
headFinder()
The HeadFinder to use for your treebank.
|
Lexicon |
lex(Options op,
Index<java.lang.String> wordIndex,
Index<java.lang.String> tagIndex)
Returns a lexicon for Arabic.
|
static void |
main(java.lang.String[] args) |
MemoryTreebank |
memoryTreebank()
Allows you to read in trees from the source you want.
|
int |
setOptionFlag(java.lang.String[] args,
int i)
Some options for setOptionFlag:
|
java.lang.String[] |
sisterSplitters()
Returns the splitting strings used for selective splits.
|
TreeTransformer |
subcategoryStripper()
Returns a TreeTransformer that retains categories
according to the following options supported by setOptionFlag:
|
Tree |
transformTree(Tree t,
Tree root)
This method does language-specific tree transformations such
as annotating particular nodes with language-relevant features.
|
TreeReaderFactory |
treeReaderFactory()
Creates an
ArabicTreeReaderFactory with parameters set
via options passed in from the command line. |
HeadFinder |
typedDependencyHeadFinder()
The HeadFinder to use when extracting typed dependencies.
|
defaultCoreNLPFlags, dependencyGrammarExtractor, generateOriginalDependencies, getGrammaticalStructure, getInputEncoding, getOutputEncoding, isEvalGF, MLEDependencyGrammarSmoothingParams, ppAttachmentEval, processHeadWord, pw, pw, readGrammaticalStructureFromFile, setEvalGF, setEvaluateGrammaticalFunctions, setGenerateOriginalDependencies, setInputEncoding, setOutputEncoding, supportsBasicDependencies, testMemoryTreebank, treebank, treebankLanguagePack, treeTokenizerFactory
public TreeReaderFactory treeReaderFactory()
ArabicTreeReaderFactory
with parameters set
via options passed in from the command line.treeReaderFactory
in interface TreebankLangParserParams
treeReaderFactory
in class AbstractTreebankParserParams
ArabicTreeReaderFactory
public MemoryTreebank memoryTreebank()
AbstractTreebankParserParams
memoryTreebank
in interface TreebankLangParserParams
memoryTreebank
in class AbstractTreebankParserParams
public DiskTreebank diskTreebank()
AbstractTreebankParserParams
diskTreebank
in interface TreebankLangParserParams
diskTreebank
in class AbstractTreebankParserParams
public HeadFinder headFinder()
AbstractTreebankParserParams
headFinder
in interface TreebankLangParserParams
headFinder
in class AbstractTreebankParserParams
public HeadFinder typedDependencyHeadFinder()
AbstractTreebankParserParams
typedDependencyHeadFinder
in interface TreebankLangParserParams
typedDependencyHeadFinder
in class AbstractTreebankParserParams
public Lexicon lex(Options op, Index<java.lang.String> wordIndex, Index<java.lang.String> tagIndex)
lex
in interface TreebankLangParserParams
lex
in class AbstractTreebankParserParams
op
- Lexicon optionspublic java.util.List<? extends HasWord> defaultTestSentence()
defaultTestSentence
in interface TreebankLangParserParams
defaultTestSentence
in class AbstractTreebankParserParams
public TreeTransformer subcategoryStripper()
-retainNPTmp
Retain temporal NP marking on NPs.
-retainNPSbj
Retain NP subject function tags
-markPRDverbs
Retain PRD verbs.
subcategoryStripper
in interface TreebankLangParserParams
subcategoryStripper
in class AbstractTreebankParserParams
public AbstractCollinizer collinizer()
collinizer
in interface TreebankLangParserParams
collinizer
in class AbstractTreebankParserParams
public AbstractCollinizer collinizerEvalb()
collinizerEvalb
in interface TreebankLangParserParams
collinizerEvalb
in class AbstractTreebankParserParams
public java.lang.String[] sisterSplitters()
AbstractTreebankParserParams
sisterSplitters
in interface TreebankLangParserParams
sisterSplitters
in class AbstractTreebankParserParams
public Tree transformTree(Tree t, Tree root)
AbstractTreebankParserParams
t
. It changes both
labels and the tree shape.transformTree
in interface TreebankLangParserParams
transformTree
in class AbstractTreebankParserParams
t
- The input tree (with non-language specific annotation already
done, so you need to strip back to basic categories)root
- The root of the current tree (can be null for words)public void display()
AbstractTreebankParserParams
display
in interface TreebankLangParserParams
display
in class AbstractTreebankParserParams
public int setOptionFlag(java.lang.String[] args, int i)
-retainNPTmp
Retain temporal NP marking on NPs.
-retainNPSbj
Retain NP subject function tags
-markGappedVP
marked gapped VPs.
-collinizerRetainsPunctuation
does what it says.
setOptionFlag
in interface TreebankLangParserParams
setOptionFlag
in class AbstractTreebankParserParams
args
- flag arguments (usually from commmand linei
- index at which to begin argument processingpublic static void main(java.lang.String[] args)
args
-